Phishing triage

Use case Β· Security

← All use cases
βœ‰

Phishing triage

Security

Classify a reported email as Phishing / Spam / Safe with the indicators (spoofing, links, urgency) and the action β€” built for real-time, high-volume inbox triage.

The routing recipe
Job typeClassification / routingPolicyFastest that passes
routes to
GPT-OSS 20B groq
groq:openai/gpt-oss-20b
92.7
match score
84.6
task fit
100
cost
96.4
speed
Why this model from benchmarks & capabilities
  • "Classification / routing" leans hardest on instruction; GPT-OSS 20B scores 78/100 there β€” #23 of 40.
  • Strength on this class of work shows up on IFEval, MMLU (zero-shot), where OpenAI (open-weight) models are competitive.
  • Cost: free tier. Speed: ~1000 tok/s on Groq LPU.
  • Chosen over Llama 3.1 8B Instant for higher task-fit (84.6 vs 75.6) & cheaper.
Capability the job needsWeightGPT-OSS 20BCatalog rank
instruction0.9078#23 of 40
speed0.9096#1 of 40
knowledge0.3070#26 of 40
Relevant benchmarksIFEval MMLU (zero-shot) EconomicsCost: free tier.
Speed: ~1000 tok/s on Groq LPU.
vs runner-upChosen over Llama 3.1 8B Instant for higher task-fit (84.6 vs 75.6) & cheaper. (Llama 3.1 8B Instant, score 86.3)
Example result
Sample input β–Ύ
From: [email protected] β€” Subject: "Your password expires today." Body: "Click here to keep your account active: http://bit.ly/xy12. Failure to act will lock your mailbox in 2 hours."
Verdict: PHISHING (confidence 96). Indicators: (1) look-alike domain "micros0ft-secure.com" (zero-for-o); (2) shortened link hiding the real destination; (3) manufactured urgency + account-lock threat. Action: Quarantine and Warn user. ESCALATE β€” credential-harvesting pattern.
Test it on your own data
Sign in to continue

LLM Switchboard is private β€” sign in with Authlee to access the control room.

Sign in with Authlee
← Back to home